Strategic induction of decision trees

An algorithm for decision-tree induction is presented in which attribute se lection is based on the evidence-gathering strategies used by doctors in se quential diagnosis. Since the attribute selected by the algorithm at a give n node is often the best attribute according to the Quinlan's information g ain criterion, the decision tree it induces is often identical to the ID3 t ree when the number of attributes is small. In problem-solving applications of the induced decision tree, an advantage of the approach is that the rel evance of a selected attribute or test can be explained in strategic terms. An implementation of the algorithm in an environment providing integrated support for incremental learning, problem solving and explanation is presen ted. (C) 1999 Elsevier Science B.V. All rights reserved.